FORECASTING THE CABLE LINES RESOURCE USING THE METHOD OF ARTIFICIAL NEURAL NETWORKS
Abstract
The article is devoted to the research of thermal fluctuation processes in accordance with the theory of thermal conductivity to solve the problems of diagnosis and prediction of the residual life of insulating materials on the basis of non-destructive temperature method. The urgency of the problem of creating neural networks for assessing the capacity, calculation and prediction of the temperature of PCL cores in real time based on the data of the temperature monitoring system, taking into account changes in the current load of the line and the external conditions of the heat sink. The problems of creation of diagnostics and forecasting of thermofluctuation processes of insulating materials of power cable lines (PCL) of electric power systems on the basis of such methods of artificial intelligence as neural networks and fuzzy logic are considered. A neural net-work was developed to determine the temperature regime of the current-carrying core of the pow-er cable. A comparative analysis of the experimental and calculated characteristics of the temper-ature distributions was carried out, and various load modes and functions of the cable current change were investigated. When analyzing the data, it was determined that the maximum deviation of the data obtained from the neural network from the training sample data was less than 10%, which is an acceptable result. To improve the accuracy, a large amount of input and output data was used in the training of the network, as well as some refinement of its structure. The developed digital hardware device measures the temperature of the surface and the environment of the power cable, and then in real time allows you to calculate its internal temperatures and solve the prob-lem of early detection of damage developing in it. The main field of application of the developed neural network for determining the temperature regime of the current-carrying conductor is the diagnosis and prediction of the electrical insulation resource (EIR) of the power cable. The model allows you to evaluate the current state of isolation and predict the residual life of the PCL. The development of an intelligent system for predicting the temperature of the PCL core contributes to the planning of the power grid operation modes in order to improve the reliability and energy efficiency of their interaction with the combined power system.
References
2. Dubyago M.N. Mathematical description of interaction of the elements in the power network system // 2013 International Conference on Renewable Energy and Environmental Technology (ICREET 2013) Applied Mechanics and Materials. – Switzerland: Trans Tech Publications, 2014. – Vol. 448-453. – P. 2455-2460.
3. Дубяго М.Н. Разработка модели старения и определение остаточного ресурса изоляции силовых кабелей // Известия ЮФУ. Технические науки. – 2014. – № 4 (153). – С. 107-114.
4. Дубяго М.Н., Полуянович Н.К. Пшихопов В.Х. Оценка и прогнозирование изоляционных материалов силовых кабельных линий // Известия ЮФУ. Технические науки. – 2015. – № 7 (168). – С. 230-237.
5. Дубяго М.Н., Полуянович Н.К. Метод селекции сигнала ЧР с помощью Вейвлет-преобразования // Известия ЮФУ. Технические науки. – 2013. – № 2 (139). – С. 99-104.
6. Poluyanovich N.K. Dubyago M.N. Study of characteristics of partial discharge for assessment of condition of electrical insulating materials of power supply system // 2013 4th International Conference on Applied Mechanics and Mechanical Engineering (ICAMME 2013), October 11-12, 2013, Singapore, Applied Mechanics and Materials. Vols. 459. Trans Tech Publications, Switzer-land, 2014. – P. 70-75.
7. Dubyago Marina N., Poluyanovich Nikolay K. Analysis of Insulation Materials of Cable Sys-tems by Method of Partial Discharges // Advances in Materials Science and Applications. – Mar. 2015. – Vol. 4, Iss. 1. – P. 23-32.
8. Dubyago M.N. and Poluyanovich N.K. Prediction of residual life of isolating materials in the process of thermal power equipment deterioration // International Conference on Advances in Energy, Environment and Chemical Engineering (AEECE 2015), September 26-27, 2015 in Changsha, China. Published by Atlantis Press. – P. 49-54. – ISSN: 2352-5401.
9. Dubyago M.N. & Poluyanovich N.K. Thermal processes of the isolating materials in problems of nondestructive diagnostics of the main and distributive power stations // IOP Conference Series: Materials Science and Engineering. 229. – 2017.
10. Dubyago M.N. and Poluyanovich N.K. Prediction of residual life of isolating materials in the process of thermal power equipment deterioration // 2017 2nd International Conference on Advanced Materials Research and Manufacturing Technologies (AMRMT 2017) 2–5 August 2017, Phuket, ThailandIOP Conference Series: Materials Science and Engineering. – 2017. – Vol. 229. 012036/. – ISSN:1757-899X. 11. Dubyago M.N., Poluyanovich N.K. Thermal processes of the isolating materials in problems of nondestructive diagnostics of the main and distributive power stations. EAI Endorsed Transac-tions on Energy Web and Information Technologies 18(16): e3. ж. SJR SCImago Journal & Coutry Rank.
12. Dubyago Marina N. and Poluyanovich Nikolay K. Estimation of Insulating Materials Depreciation and Forecasting the Residual Cable Resource Considering the Current Core Temperature // Interna-tional Journal of Materials, Mechanics and Manufacturing. – 2019. – Vol. 7, No. 1. – P. 415-420.
13. Шумилова Г.П., Готман Н.Э., Старцева Т.Б. Прогнозирование электрических нагрузок ЭЭС с использованием методов искусственного интеллекта // Сб. трудов Российского национального симпозиума по энергетике. Казань, 10–14 сент. 2001 г. – М.: КГЭУ, 2001. – С. 103-106.
14. Хайкин С. Нейронные сети: полный курс. – 2-е изд. – М.: Изд. дом «Вильямс», 2006. – 1104 с.
15. Рутковская Д., Пилиньский М., Рутковский Л. Нейронные сети, генетические алгоритмы и нечеткие системы: пер. с польск. И.Д. Рудинского. – М.: Горячая линия – Телеком, 2008. – 452 с.
16. Лавренков Ю.Н. Исследование и разработка комбинированных нейросетевых техноло-гий для повышения эффективности безопасной маршрутизации информации в сетях связи: дисс. … канд. техн. наук. – М.: МГТУ, 2014. – C. 17-21.
17. Короткевич М.А., Курачинский В.В. Прогнозирование электрической нагрузки энерго-системы на следующие сутки с использованием метода искусственных нейронных сетей // Энергетика. Известия высших учебных заведений и энергетических объединений СНГ.– 2010. – № 2. – С. 5-11.
18. Финаев В.И. Модели систем принятия решений. – Таганрог: Изд-во ТРТУ, 2005. – 118 c.
19. Гайдук А.Р. Системы автоматизированного управления. Примеры, анализ и синтез. – Таганрог: Изд-во ТРТУ, 2006. – 414 с.
20. Шутенко О.В., Загайнова А.А., Сердюкова Г.Н. Анализ влияния условий и режимов эксплуатации на техническое состояние основной изоляции высоковольтных вводов различной конструкции // Электротехника и электромеханика. – 2019. – № 1. – С. 57-65.
